LLM Code Generation

LLM: Large Language Model

This field studies how large language models generate, edit, translate, and test programs from natural-language instructions, examples, or existing code. Common approaches include prompting and retrieval, fine-tuning and reinforcement learning, constrained decoding, and agentic loops that use execution, tests, or static analysis to refine outputs. Evaluations range from HumanEval, MBPP, and LiveCodeBench to repository-level and domain-specific tasks, increasingly measuring security, efficiency, and adherence to requirements alongside whether code runs. Models have improved on standard benchmarks, but reliability on unfamiliar APIs, complex projects, specialized languages, and implicit requirements remains a challenge, as do trade-offs among correctness, safety, cost, and maintainability.

Latest papers

314 papers23 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Mar 6, 2026Juyong Jiang, Jiasi Shen, Sunghun Kim +3LLM Code Generation LLM Self-Correction
The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology · Amazon AGI +1
Python Bindings for a Large C++ Robotics Library: The Case of OMPL
Mar 4, 2026Weihang Guo, Theodoros Tyrovouzis, Lydia E. KavrakiCode Generation LLM Code Generation
Department of Computer Science, Rice University, Houston TX, USA · Ken Kennedy Institute at Rice University
CONCUR: Benchmarking LLMs for Concurrent Code Generation
Mar 4, 2026Jue Huang, Tarek Mahmud, Corina Pasareanu +1Code Generation Evaluation Code Generation Benchmarks
The University of Queensland · Texas A&M University - Kingsville · Carnegie Mellon University
An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code
Mar 3, 2026Sophie Weidmann, Fernando CastorCode Generation LLM Code Generation
University of Twente, Enschede, The Netherlands
Locally Coherent Parallel Decoding in Diffusion Language Models
Mar 3, 2026Michael Hersche, Nicolas Menet, Ronan Tanios +1Parallel Decoding for Diffusion Language Models Diffusion Language Model Decoding
IBM Research - Zurich · Department of Computer Science, ETH Zürich
GenDB: The Next Generation of Query Processing -- Synthesized, Not Engineered
Mar 2, 2026Jiale Lao, Immanuel TrummerLLM Code Generation
Cornell University
Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision
Mar 2, 2026Manisha Mukherjee, Vincent J. HellendoornLLM Safety Secure Code Generation
Carnegie Mellon University, Pittsburgh, PA, USA
From Stochastic Answers to Verifiable Reasoning: Interpretable Decision-Making with LLM-Generated Code
Feb 28, 2026Anirudh Jaidev Mahesh, Ben Griffin, Fuat Alican +8Rare-Event Prediction LLM Decision-Making
Georgia Institute of Technology · University of Oxford · Vela Research +1
Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution
Feb 27, 2026Tinglin Huang, Bo Chen, Xiao Zhang +2Synthetic Data Generation for Language Models Code Generation
Yale University · ByteDance Seed
Utilizing LLMs for Industrial Process Automation
Feb 26, 2026Salim FaresIndustrial Automation Automated Software Engineering
University of Passau, Passau, Germany
Enhancing LLM-Based Test Generation by Eliminating Covered Code
Feb 25, 2026WeiZhe Xu, Mengyu Liu, Fanxin KongAutomated Test Generation LLM Code Generation
University of Notre Dame, Notre Dame, IN, USA · Washington State University, Richland, WA, USA
An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention
Feb 25, 2026Madhusudan Ghosh, Rishabh GuptaLong-Context Modeling Long-Context Language Model Evaluation
Indian Association for the Cultivation of Science, Kolkata, India · Bosch Research and Technology Centre, Bangalore, India
From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation
Feb 24, 2026Linus Bantel, Moritz Strack, Alexander Strack +1Code Generation LLM Code Generation
Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, Germany
CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
Feb 23, 2026Jingwei Shi, Xinxiang Yin, Jing Huang +2Automated Test Generation Adversarial Scenario Generation
Shanghai University of Finance and Economics · Northwestern Polytechnical University · Meituan +1
Mitigating "Epistemic Debt" in Generative AI-Scaffolded Novice Programming using Metacognitive Scripts
Feb 22, 2026Sreecharan SankaranarayananGenerative AI in Education AI in Education
Extuitive Inc. (Flagship Pioneering) Cambridge, Massachusetts, United States of America
Automated Generation of Microfluidic Netlists using Large Language Models
Feb 22, 2026Jasper Davidson, Skylar Stockham, Allen Boston +3Program Synthesis LLM Code Generation
Department of Electrical and Computer Engineering, University of Utah · Primis AI, Inc.
Operational Robustness of LLMs on Code Generation
Feb 21, 2026Debalina Ghosh Paul, Hong Zhu, Ian BayleyLanguage Model Robustness LLM Code Generation
School of Engineering, Computing and Mathematics, Oxford Brookes University Oxford, OX3 0BP, United Kingdom
SecCodeBench-V2 Technical Report
Feb 17, 2026Longfei Chen, Ji Zhao, Lanxiao Cui +24Secure Code Generation Code Generation Benchmarks
TSINGHUA UNIVERSITY, BEIJING, CHINA · ALIBABA GROUP, HANGZHOU, CHINA
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Feb 17, 2026Chansung Park, Juyong Jiang, Fan Wang +4LLM Code Generation RL for Code Generation
Electronics and Telecommunications Research Institute · The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology +2
SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning
Jan 29, 2026Jinjun Peng, Magnus Saebo, Tianjun Zhong +5Small Language Models LLM Code Generation
Department of Computer Science, Columbia University, New York, USA · Computer Science Department, University of California, Los Angeles, California, USA.
HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation
Jan 20, 2026Qirui Chen, Jingxian Shuai, Shuangwu Chen +8LLM Security Secure Code Generation
University of Science and Technology of China, China · Xi’an Jiaotong University, China · Nanjing University, China +1
QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models
Jan 13, 2026Zhaolu Kang, Junhao Gong, Wenqing Hu +13Financial Language Model Evaluation LLM Evaluation
Peking University · Tsinghua University · Fudan University +6
X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests
Jan 11, 2026Jie Wu, Haoling Li, Xin Zhang +8RL for Code Generation Synthetic Data Generation
Tsinghua University · Microsoft
Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition
Jan 8, 2026Nils EineckeAI-Assisted Scientific Research Human-AI Collaboration
Honda Research Institute Europe GmbH, Offenbach, Germany
SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models
Dec 20, 2025Scott ThorntonSoftware Security LLM Security
DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
Nov 24, 2025Rupam Patir, Keyan Guo, Suvadra Barua +5LLM Code Generation Secure Code Generation
University at Buffalo, SUNY
Learning Bug Context for PyTorch-to-JAX Translation with LLMs
Oct 10, 2025Hung Phan, Son Vu, Tuan Dinh +3Code Translation LLM Code Generation
Department of Computer Science, Iowa State University, Ames, IA, USA · Department of Human Science, Iowa State University, Ames, IA, USA · Subquadratic AI, Miami, Florida, USA +1
Investigating The Smells of LLM Generated Code
Oct 3, 2025Debalina Ghosh Paul, Hong Zhu, Ian BayleySoftware Engineering Code Generation Evaluation
School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, OX3 0BP, UK
VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
Sep 27, 2025Jiayu Zhao, Zehua Pei, Zetao Guo +2RTL Code Generation LLM Code Generation
University of Science and Technology of China
Benchmarking Web API Integration Code Generation
Sep 24, 2025Daniel Maninger, Leon Chemnitz, Amir Molzam Sharifloo +2Code Generation Code Generation Evaluation
Technische Universität Darmstadt, Germany · Hessian Center for Artificial Intelligence (hessian.AI), Germany · Pariton AI, Germany +1

Mar 6, 2026J/K move · Enter open · S save

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

Juyong Jiang, Jiasi Shen, Sunghun Kim, Kang Min Yoo+2

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology · Amazon AGI+1

LLM Code Generation LLM Self-Correction LLM Self-Refinement RL for Code Generation

Open paper AskPDF arXiv

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model's weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-only training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B to 14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, efficient reasoning and reflection patterns. The source code and data are available at https://github.com/juyongjiang/ReflexiCoder.